apex-dev-skills

Route and govern delegation: a compiled routing policy picks the tier, provider, fan-out and review shape for each task or ad-hoc ask; PreToolUse/SubagentStop hooks enforce it; provider shims run external workers; every route, spawn, worker run and verdict lands in a hash-chained ledger, which report.sh --per-task prices per routed task. Drives apex-scope-loop as its execution engine.

2 skills · 6 commands · 10 agents · hooks

Typed, probability-carrying answers for the questions apex-dispatch and apex-scope-loop leave to judgment (task class, risk tier): one CLI, rubric files, a fail-closed validator for every backend, tri-state uncertainty, and calibration that only a measurement job can grant. Off until a repo opts in; absent, slow or unconfigured, routing stays table-only.

1 skill · 5 commands · hooks

Routing and gate engine for apex-app: lanes + surface-ledger routing, cross-platform guardrails, and phases that close on computed obligations.

2 skills · 4 commands · hooks

Decide -> plan -> loop: SPARC-shaped ADR + phased plan authoring with scope sizing (bugfix, poc, feature) and an intent round, autonomous /loop + /schedule execution, per-phase swarm dispatch, The Gibson's harness gates (baseline green gate, independent review, Tier-C human approval), and an operate phase that watches landed plans against their declared checks.

2 skills · 3 commands · 2 agents

Trace, replay, and cost-attribute multi-agent runs: hook-driven JSONL AgentTrace, deterministic OrchestrationReplay, and per-subagent TokenLens — pure artifacts, with an optional read-only MCP dashboard server.

3 skills · 1 command · 1 MCP server · hooks

Interview-first greenfield project initializer: opens with 'what are you trying to build?', researches the context, then scaffolds a fully-governed repo (paved-road defaults), provisions the Apex-Dev-Skills suite (plus optional ruflo), and verifies it before the first commit. Generated projects are steered to build features via apex-plan/apex-loop. Supports TypeScript/JavaScript, Python, Go, and Rust.

3 skills · 1 command · 1 agent

Tool-contract validation + runtime reliability: a PostToolUse ledger that infers per-tool schemas and flags contract drift, plus FlakeGuard detection of non-deterministic agent failures (retries, partial failures, flaky tools).

2 skills · 1 command · hooks

Diagnose RAG/embedding/memory lifecycle health: audit chunking, detect embedding-model drift, find stale vectors, and regression-test retrieval recall with a golden Q/A harness. Not a vendor connector — it diagnoses retrieval quality.

2 skills · 1 command · 1 MCP server

Agent-team coordination tooling: TeamLint statically audits subagent/agent-team config before a run, and ContextBudget hooks warn before compaction silently drops critical state.

1 skill · 1 command · hooks

Deterministic runtime guardrails via PreToolUse hooks: hard-block edits to sensitive paths, deny destructive bash, scan tool inputs for secrets, and compile a declarative YAML policy into enforced matcher config.

1 skill · 1 command · hooks

Understand and safely change legacy or AI-generated code: pin current behavior with characterization tests before refactoring, and build a living system map of an unfamiliar codebase in an isolated subagent context.

1 skill · 1 command · 1 agent

A local admin console for apex-scope-loop, apex-dispatch and apex-decision-layer: manage API keys, see progress per repo, plan and task (with scope, intent, each landed plan's operate state and per-task cost, read-only), measure the software factory (Uber's cost equation, cost per outcome paired with quality, and flow and integrity metrics) against your own targets, and turn the knobs each plugin honours (review strictness, tier definitions, reviewers and providers, decision-layer config) with a kill switch and an undoable audit log. An admin layer: it never starts or drives work.

1 command